Bachelorarbeit BCLR-0143

Göttlich, Philipp: Ein interaktiver Ansatz zur visuellen Analyse von Trajektorien basierend auf einem Partition-and-Group Clustering Framework.
Universität Stuttgart, Fakultät Informatik, Elektrotechnik und Informationstechnik, Bachelorarbeit Nr. 143 (2014).
61 Seiten, deutsch.
CR-Klassif.D.2.2 (Software Engineering Design Tools and Techniques)
D.2.6 (Software Engineering Programming Environments)
H.2.8 (Database Applications)
H.3.3 (Information Search and Retrieval)
I.4.6 (Image Processing and Computer Vision Segmentation)
I.5.2 (Pattern Recognition Design Methodology)
I.5.3 (Pattern Recognition Clustering)
I.5.5 (Pattern Recognition Implementation)

Since movements can be tracked easier by the help of GPS-sensors, the quantity of movement data rises rapidly. These can potentially exhibit many behavioural patterns which provide valuable insights for investigation or protection of moving objects. In order to find such patterns, the unstructered data must be processed and visualised. This enables their following analysis. To increase the transparency of this process and to support the user in the analysis, the opportunities of interaction are an important issue. So far, interactive actions for the visual analysis of movement data are pared down to a minimum and are used only for the exploration of the results of the processing. That is why, in this thesis, we develop a framework which firmly connects automatic data processing through interactive methods with visualisation in order to improve the capabilities of analysis and interaction. Therefore, a partition method, a cluster algorithm, and an adjustable distance function are combined by a continuous interactive visualisation in order to support analysts towards the understanding and directing of the extraction of patterns and the concluding analysis. To show what makes this approach distinguishable from existing approaches, the utilised components will be explained in detail, innovations will be illustrated, and advantages and disadvantages will be explained.

Volltext und
andere Links
PDF (5570131 Bytes)
Abteilung(en)Universität Stuttgart, Institut für Visualisierung und Interaktive Systeme, Visualisierung und Interaktive Systeme
BetreuerKrueger, Robert
Eingabedatum20. Januar 2015
   Publ. Informatik